David Abel (@dabelcs) - Twitterプロフィール

固定されたツイート

David Abel@dabelcs·4 Kas

Thrilled to share our new #NeurIPS2025 paper done at @GoogleDeepMind, Plasticity as the Mirror of Empowerment We prove every agent faces a trade-off between its capacity to adapt (plasticity) and its capacity to steer (empowerment) Paper: david-abel.github.io/plasticity.pdf 🧵🧵🧵👇

English

25

67

449

101.4K

David Abel がリツイート

Hadi Vafaii@hadivafaii·16 Mar

The "decoupling of information and energy" is a major point of divergence between biological and artificial computers. Brains are efficient, modern AI isn't. And energy consumption is the biggest bottleneck in scaling AI (you can't hallucinate electrons into existence). To address this we need an "energy-aware theory of computation." And this new preprint is an attempt to address this. [1/11] 🧵

English

17

74

340

51K

David Abel がリツイート

Hadi Vafaii@hadivafaii·6 Mar

Newton gave force, inertia, and motion precise mathematical definitions. This unlocked centuries of progress in mechanics. Turing did it for "computation," and Shannon for "information." Today, "agency" still feels a bit like "computation" before Turing: everybody uses the word, but there is no widely accepted precise definition. @dabelcs argue that RL needs to take this problem more seriously. [1/3]🧵

English

7

41

372

20.3K

David Abel がリツイート

Samuel Garcin@SamuelGarcin·5 Mar

PERSIST is a world model that ditches pixel-based histories for a 3D world state. Instead of searching through an ever-growing sequence of past pixel observations, PERSIST retrieves spatial information from a dynamically evolving 3D representation. This change improves the spatial memory, 3D consistency, and long-horizon stability of the model, enabling interactive experiences within coherent and evolving 3D worlds. #MachineLearning #WorldModels #GenerativeAI #3DComputerVision #ComputerVision #Genie3 #AI

English

13

46

415

25.5K

David Abel がリツイート

Ian Osband@IanOsband·5 Mar

Assembling a team at DeepMind in London. Scaling up RL for post-training is working, but right now it's still mostly hacks and dark arts (pretraining circa 2019). Pre-training wasn't always scaling laws and log-log plots; someone had to find the simplicity. We aim to do the same. If you're interested in doing things right in a research-first environment that scales all the way, please apply: job-boards.greenhouse.io/deepmind/jobs/…

English

19

64

999

149.4K

David Abel がリツイート

Gillian Hadfield@ghadfield·16 Ara

Hiring a postdoc for the Normativity Lab at Johns Hopkins (2026 start). Looking for multiagent systems expertise (RL/generative agents) + interdisciplinary background in AI and cognitive science/econ/cultural evolution. apply.interfolio.com/177701

English

0

6

21

2.2K

David Abel がリツイート

Alison Gopnik@AlisonGopnik·10 Ara

New preprint in advance of a Phil Trans paper. Outlining a theoretical argument bridging Bayesian causal learning and empowerment in reinforcement learning. And empirical data that kids do too! arxiv.org/abs/2512.08230

English

0

4

28

7.9K

David Abel がリツイート

Iason Gabriel@IasonGabriel·1 Ara

🚨Exciting new opportunity🚨 Come and work with me and a fantastic team @GoogleDeepMind exploring the political, economic, social and cultural impact of advanced AI technology, including AGI and beyond! The details and application link can be found below!

English

24

48

505

173.4K

David Abel@dabelcs·9 Ara

@ma_tay_ @humansand Congratulations Taylor!!

English

2

0

2

430

Taylor Sorensen@ma_tay_·7 Ara

Also happy to share that I've joined @humansand!! More details in the coming days, but I am SO excited to build AI to work with and be good for humans!

English

20

7

190

19.8K

David Abel@dabelcs·7 Ara

Amazing opportunity to work with @ermgrant

Erin Grant@ermgrant

Thrilled to announce I'll start in 2026 as faculty in Psych & CS @UAlberta + @AmiiThinks Fellow!! 🥳 Recruiting students to develop theories of cognition in natural and artificial systems 🤖💭🧠. Find me at #NeurIPS2025 workshops (talk at @CogInterp & organising @DataOnBrainMind)

English

0

1

15

4.1K

David Abel がリツイート

Erin Grant@ermgrant·6 Ara

Thrilled to announce I'll start in 2026 as faculty in Psych & CS @UAlberta + @AmiiThinks Fellow!! 🥳 Recruiting students to develop theories of cognition in natural and artificial systems 🤖💭🧠. Find me at #NeurIPS2025 workshops (talk at @CogInterp & organising @DataOnBrainMind)

English

9

20

198

24.8K

David Abel@dabelcs·7 Ara

@laurinpaech @GoogleDeepMind Great to meet you as well, thanks for the discussion!

English

0

16

Laurin@laurinpaech·7 Ara

@dabelcs @GoogleDeepMind Was great meeting you and getting some additional insights!

English

1

0

1

11

David Abel@dabelcs·4 Kas

Thrilled to share our new #NeurIPS2025 paper done at @GoogleDeepMind, Plasticity as the Mirror of Empowerment We prove every agent faces a trade-off between its capacity to adapt (plasticity) and its capacity to steer (empowerment) Paper: david-abel.github.io/plasticity.pdf 🧵🧵🧵👇

English

25

67

449

101.4K

David Abel@dabelcs·4 Ara

@tw_killian 😁 yes please come by would love to see you!

English

0

2

118

Taylor W. Killian@tw_killian·4 Ara

@dabelcs Yes, somewhere you're tied down so I can finally see you!

English

1

0

2

235

David Abel@dabelcs·4 Ara

Interested in the theory of agents / definitions / RL under minimal assumptions? I'll be at poster #512 today (Thurs.) in the 4.30pm-7.30pm session. Come on by 🙂

David Abel@dabelcs

Thrilled to share our new #NeurIPS2025 paper done at @GoogleDeepMind, Plasticity as the Mirror of Empowerment We prove every agent faces a trade-off between its capacity to adapt (plasticity) and its capacity to steer (empowerment) Paper: david-abel.github.io/plasticity.pdf 🧵🧵🧵👇

English

3

10

67

7.7K

David Abel@dabelcs·3 Ara

This is a very thoughtful paper They give a careful construction of an agent that is embedded in its environment: go talk to Alex!

Alex Lewandowski@axlewandowski

At NeurIPS and interested in continual learning? Stop by our spotlight poster this Friday @ 11am (#508). Our work provides a computational approach to the big world hypothesis through embedded agents. Feel free to reach out if you want to meet up while in San Diego!

English

0

1

37

4.7K

David Abel がリツイート

Alex Lewandowski@axlewandowski·3 Ara

At NeurIPS and interested in continual learning? Stop by our spotlight poster this Friday @ 11am (#508). Our work provides a computational approach to the big world hypothesis through embedded agents. Feel free to reach out if you want to meet up while in San Diego!

English

1

8

47

7.1K

David Abel がリツイート

bigAI@BrownBigAI·3 Ara

Skill-Driven Neurosymbolic State Abstractions, led by Alper Ahmetoglu @alperahmetoglu, Steven James, Cam Allen @camall3n, Sam Lobel, David Abel @dabelcs, and George Konidaris. Check out our poster on Wednesday at #413 between 4:30-7:30. 8/8 openreview.net/forum?id=ggP2r…

English

0

3

15

863

David Abel がリツイート

Trevor McInroe@trevormcinroe·1 Ara

Introducing Terra Nova, a new comprehensive challenge environment for RL research inspired by Civilization V.

English

4

6

47

4.7K

David Abel がリツイート

Daniel Furelos-Blanco@_danielfb·30 Kas

It was a pleasure to have @dabelcs present this work last October at @SPIKE_ICL! 📽️ The recording of the talk is now available: youtube.com/watch?v=XWxP_q… Don't miss their poster at #NeurIPS2025 🚀

YouTube

David Abel@dabelcs

Thrilled to share our new #NeurIPS2025 paper done at @GoogleDeepMind, Plasticity as the Mirror of Empowerment We prove every agent faces a trade-off between its capacity to adapt (plasticity) and its capacity to steer (empowerment) Paper: david-abel.github.io/plasticity.pdf 🧵🧵🧵👇

English

0

1

6

870

David Abel がリツイート

edo@edov_i·27 Kas

@giffmana MDP is the worst thing about RL, beating the 'starting-from-scratch' every time. That's why I liked this paper arxiv.org/abs/2407.10583

English

0

1

27

2.7K

David Abel がリツイート

Kale-ab Tessera@KaliTessera·26 Kas

Thrilled to present HyperMARL at #NeurIPS2025 in San Diego next week! 🚀 (Amos will present at @EurIPSConf too.) TL;DR: Coupling obs and agent IDs can hurt perf in MARL. Agent-conditioned hypernets cleanly decouple grads and enable specialisation. 📜: arxiv.org/abs/2412.04233

Kale-ab Tessera@KaliTessera

📜🤖 Can a shared multi-agent RL policy support both specialised & homogeneous team behaviours -- without changing the learning objective, requiring preset diversity levels or sequential updates? Our preprint “HyperMARL: Adaptive Hypernetworks for Multi-Agent RL” explores this!

English

3

1

25

2.4K

David Abel

ディスカバー